Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    11

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squared
    -0.08
     şun
    -0.06
    军
    -0.06
    ID
    -0.06
    (ag
    -0.06
    utow
    -0.06
    hp
    -0.06
    .cycle
    -0.06
    Err
    -0.06
    omics
    -0.06
    POSITIVE LOGITS
     XmlDocument
    0.07
    .RequestMethod
    0.07
    .Some
    0.06
     mundane
    0.06
     Českosloven
    0.06
    <SpriteRenderer
    0.06
     Incontri
    0.06
    ーター
    0.06
    ";
↵
↵
    0.06
     Πολι
    0.06
    Act Density 0.026%

    No Known Activations